Click any tag below to further narrow down your results
Links
Google has made Gemini Omni 1.2 Flash generally available, a video generation model that now produces 15-second clips and costs 30% less than the previous version. It adds multi-turn editing, tighter consistency across shots, and more natural speech and camera control.
- Price drops 30% from Omni 1.1 to $0.07 per second for 720p video, with a draft-at-low-res, upscale-later workflow to keep costs down.
- Clips can now run up to 15 seconds, up from 10, with duration set in one-second steps from 3 to 15.
- You can refine a clip turn by turn (swap backgrounds, change lighting, switch aspect ratio) without regenerating the whole thing.
- Character, product, and brand details like faces, garments, and packaging typography are meant to stay consistent across angles and shots.
@gabegreenberg on X
Ben Affleck says he writes Python, understands convolutional neural networks, and has worked with GPUs for years, and that he got private looks at Google's and OpenAI's video models by simply asking. The exchange is a casual interview, so the technical claims are self-reported and not independently verified.
- Affleck says his visual-effects background, including a small VFX company before Artists Equity, led him to machine learning, and that he's worked extensively with GPUs.
- He describes images as tensors (batch, frame, and RGB values per pixel) and convolutional networks as tools for edge detection and feature extraction, such as isolating a window ledge for green-screen replacement.
- He says he was invited to see Google's and OpenAI's transformer-based video work, and that people sometimes agree to show him, "to my astonishment."